{"id":"https://openalex.org/W7223154193","doi":"https://doi.org/10.48550/arxiv.2610.27747","title":"Constant Step Sizes for Muon-Type Spectral Optimizers on Strongly Convex Quadratics","display_name":"Constant Step Sizes for Muon-Type Spectral Optimizers on Strongly Convex Quadratics","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223154193","doi":"https://doi.org/10.48550/arxiv.2610.27747"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.27747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27747","pdf_url":"https://arxiv.org/pdf/2610.27747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.27747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086696547","display_name":"Pratik Jawanpuria","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jawanpuria, Pratik","raw_affiliation_strings":["Centre for Machine Intelligence and Data Science , IIT Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Machine Intelligence and Data Science , IIT Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159163442","display_name":"Bhabatosh Garai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Garai, Bhabatosh","raw_affiliation_strings":["Centre for Machine Intelligence and Data Science , IIT Bombay , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Machine Intelligence and Data Science , IIT Bombay , India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023551959","display_name":"Bamdev Mishra","orcid":"https://orcid.org/0000-0001-7430-2843","observed_orcids":["https://orcid.org/0000-0001-7430-2843"]},"institutions":[{"id":"https://openalex.org/I4210162141","display_name":"Microsoft (India)","ror":"https://ror.org/04ww0w091","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210162141"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mishra, Bamdev","raw_affiliation_strings":["Microsoft , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft , India","institution_ids":["https://openalex.org/I4210162141"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8931000232696533,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.8931000232696533,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.0640999972820282,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.02810000069439411,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/muon-optimizer","display_name":"Muon optimizer","score":0.9290000200271606},{"id":"https://openalex.org/keywords/constant-step-size","display_name":"constant step size","score":0.9470000267028809},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"singular value decomposition","score":0.4320000112056732},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.732699990272522},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5311999917030334},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.421099990606308},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C146324458","wikidata":"https://www.wikidata.org/wiki/Q1202673","display_name":"Uniform norm","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C92207270","wikidata":"https://www.wikidata.org/wiki/Q939253","display_name":"Matrix norm","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2776637919","wikidata":"https://www.wikidata.org/wiki/Q624380","display_name":"Descent (aeronautics)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.27747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27747","pdf_url":"https://arxiv.org/pdf/2610.27747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.27747","doi":"https://doi.org/10.48550/arxiv.2610.27747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.27747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.27747","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.27747","pdf_url":"https://arxiv.org/pdf/2610.27747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223154193.pdf","grobid_xml":"https://content.openalex.org/works/W7223154193.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2786602455","https://openalex.org/W2911863041","https://openalex.org/W4403815243","https://openalex.org/W4407212433","https://openalex.org/W4407424967","https://openalex.org/W4414846785","https://openalex.org/W4415145305","https://openalex.org/W4416046424","https://openalex.org/W4416613161","https://openalex.org/W6966842224","https://openalex.org/W7125960423","https://openalex.org/W7128817298","https://openalex.org/W7161023354","https://openalex.org/W7161139062","https://openalex.org/W7161839150","https://openalex.org/W7204546023"],"related_works":["https://openalex.org/W7161139062","https://openalex.org/W7214796139","https://openalex.org/W7164009365","https://openalex.org/W7164857960","https://openalex.org/W7128817298","https://openalex.org/W7125282725","https://openalex.org/W7127997059","https://openalex.org/W7223289972","https://openalex.org/W7128376444","https://openalex.org/W7125923009"],"abstract_inverted_index":{"Muon":[0,159],"and":[1,44,71,107,140,173,175],"related":[2],"optimizers":[3,20],"update":[4,37,51,170],"a":[5,9,22,97,123,143],"weight":[6],"matrix":[7,29],"with":[8,21,92,96,118,129,142],"spectrally":[10],"transformed":[11],"gradient.":[12],"In":[13],"this":[14],"work,":[15],"we":[16],"study":[17],"such":[18],"spectral":[19,87],"constant":[23],"step":[24,45,110,132],"size":[25,46],"on":[26,167,177],"strongly":[27],"convex":[28],"quadratics,":[30],"which":[31,57,62,74],"isolate":[32],"the":[33,36,39,55,59,65,72,76,79,85,100,114,130,136,155,169,178,182],"effect":[34],"of":[35,41,78,158],"from":[38],"confounds":[40],"nonconvexity,":[42],"noise,":[43],"schedules.":[47],"We":[48],"analyze":[49],"an":[50,119],"using":[52],"two":[53,82],"quantities:":[54],"gain,":[56,99],"is":[58,75,171],"factor":[60],"by":[61,113,135],"it":[63],"amplifies":[64],"gradient":[66,105],"along":[67],"each":[68],"singular":[69],"direction,":[70],"length,":[73,125,145],"norm":[77],"update.":[80],"These":[81],"quantities":[83],"place":[84],"popular":[86],"updates":[88],"in":[89,161],"three":[90,163],"regimes":[91],"different":[93],"behavior:":[94],"(i)":[95],"bounded":[98],"iterates":[101],"behave":[102],"like":[103],"preconditioned":[104],"descent":[106],"converge":[108,149],"for":[109,150],"sizes":[111,133],"set":[112,134],"largest":[115],"curvature;":[116],"(ii)":[117],"unbounded":[120],"gain":[121],"but":[122],"vanishing":[124],"they":[126,146],"still":[127],"converge,":[128],"admissible":[131],"total":[137],"curvature":[138],"instead;":[139],"(iii)":[141],"non-vanishing":[144],"do":[147],"not":[148,176],"almost":[151],"every":[152],"initialization.":[153],"Interestingly,":[154],"practical":[156],"variants":[157],"fall":[160],"all":[162],"regimes,":[164],"depending":[165],"only":[166],"how":[168],"normalized":[172],"scaled":[174],"polynomial":[179],"that":[180],"approximates":[181],"polar":[183],"factor.":[184],"Experiments":[185],"validate":[186],"these":[187],"findings.":[188]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-22T00:00:00"}